Coverage for biobb_analysis/gromacs/gmx_cluster.py: 91%
64 statements
« prev ^ index » next coverage.py v7.10.6, created at 2025-09-08 10:47 +0000
1#!/usr/bin/env python3
3"""Module containing the GMX Cluster class and the command line interface."""
5from typing import Optional
6from biobb_common.generic.biobb_object import BiobbObject
7from biobb_common.tools import file_utils as fu
8from biobb_common.tools.file_utils import launchlogger
9from biobb_analysis.gromacs.common import check_input_path, check_traj_path, check_index_path, check_out_pdb_path, get_binary_path, get_image_selection, get_selection_index_file, get_dista, get_method, get_cutoff
12class GMXCluster(BiobbObject):
13 """
14 | biobb_analysis GMXCluster
15 | Wrapper of the GROMACS cluster module for clustering structures from a given GROMACS compatible trajectory.
16 | `GROMACS cluster <http://manual.gromacs.org/current/onlinehelp/gmx-cluster.html>`_ can cluster structures using several different methods. Distances between structures can be determined from a trajectory. RMS deviation after fitting or RMS deviation of atom-pair distances can be used to define the distance between structures.
18 Args:
19 input_structure_path (str): Path to the input structure file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/topology.tpr>`_. Accepted formats: tpr (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), brk (edam:format_2033), ent (edam:format_1476).
20 input_traj_path (str): Path to the GROMACS trajectory file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/trajectory.trr>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876).
21 input_index_path (str) (Optional): Path to the GROMACS index file. File type: input. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/data/gromacs/index.ndx>`_. Accepted formats: ndx (edam:format_2033).
22 output_pdb_path (str): Path to the output cluster file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gromacs/ref_cluster.pdb>`_. Accepted formats: xtc (edam:format_3875), trr (edam:format_3910), cpt (edam:format_2333), gro (edam:format_2033), g96 (edam:format_2033), pdb (edam:format_1476), tng (edam:format_3876).
23 output_cluster_log_path (str) (Optional): Path to the output log file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_cluster.log>`_. Accepted formats: log (edam:format_2330).
24 output_rmsd_cluster_xpm_path (str) (Optional):Path to the output X PixMap compatible matrix file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_rmsd-clust.xpm>`_. Accepted formats: xpm (edam:format_3599).
25 output_rmsd_dist_xvg_path (str) (Optional): Path to xvgr/xmgr file. File type: output. `Sample file <https://github.com/bioexcel/biobb_analysis/raw/master/biobb_analysis/test/reference/gmx_cluster_rmsd-dist.xvg>`_. Accepted formats: xvg (edam:format_2330).
26 properties (dic - Python dictionary object containing the tool parameters, not input/output files):
27 * **fit_selection** (*str*) - ("System") Group where the fitting will be performed. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups).
28 * **output_selection** (*str*) - ("System") Group that is going to be written in the output trajectory. If **input_index_path** provided, check the file for the accepted values. Values: System (all atoms in the system), Protein (all protein atoms), Protein-H (protein atoms excluding hydrogens), C-alpha (C-alpha atoms), Backbone (protein backbone atoms: N; C-alpha and C), MainChain (protein main chain atoms: N; C-alpha; C and O; including oxygens in C-terminus), MainChain+Cb (protein main chain atoms including C-beta), MainChain+H (protein main chain atoms including backbone amide hydrogens and hydrogens on the N-terminus), SideChain (protein side chain atoms: that is all atoms except N; C-alpha; C; O; backbone amide hydrogens and oxygens in C-terminus and hydrogens on the N-terminus), SideChain-H (protein side chain atoms excluding all hydrogens), Prot-Masses (protein atoms excluding dummy masses), non-Protein (all non-protein atoms), Water (water molecules), SOL (water molecules), non-Water (anything not covered by the Water group), Ion (any name matching an Ion entry in residuetypes.dat), NA (all NA atoms), CL (all CL atoms), Water_and_ions (combination of the Water and Ions groups).
29 * **dista** (*bool*) - (False) Use RMSD of distances instead of RMS deviation.
30 * **nofit** (*bool*) - (False) Do not use least squares fitting before RMSD calculation.
31 * **method** (*str*) - ("linkage") Method for cluster determination. Values: linkage (Add a structure to a cluster when its distance to any element of the cluster is less than cutoff), jarvis-patrick (Add a structure to a cluster when this structure and a structure in the cluster have each other as neighbors and they have a least P neighbors in common), monte-carlo (Reorder the RMSD matrix using Monte Carlo such that the order of the frames is using the smallest possible increments), diagonalization (Diagonalize the RMSD matrix), gromos (Count number of neighbors using cut-off and take structure with largest number of neighbors with all its neighbors as cluster and eliminate it from the pool of clusters).
32 * **cutoff** (*float*) - (0.1) [0~10|0.1] RMSD cut-off (nm) for two structures to be neighbor.
33 * **binary_path** (*str*) - ("gmx") Path to the GROMACS executable binary.
34 * **remove_tmp** (*bool*) - (True) [WF property] Remove temporal files.
35 * **restart** (*bool*) - (False) [WF property] Do not execute if output files exist.
36 * **sandbox_path** (*str*) - ("./") [WF property] Parent path to the sandbox directory.
37 * **container_path** (*str*) - (None) Container path definition.
38 * **container_image** (*str*) - ('gromacs/gromacs:2022.2') Container image definition.
39 * **container_volume_path** (*str*) - ('/tmp') Container volume path definition.
40 * **container_working_dir** (*str*) - (None) Container working directory definition.
41 * **container_user_id** (*str*) - (None) Container user_id definition.
42 * **container_shell_path** (*str*) - ('/bin/bash') Path to default shell inside the container.
44 Examples:
45 This is a use example of how to use the building block from Python::
47 from biobb_analysis.gromacs.gmx_cluster import gmx_cluster
48 prop = {
49 'fit_selection': 'System',
50 'output_selection': 'System',
51 'method': 'linkage'
52 }
53 gmx_cluster(input_structure_path='/path/to/myStructure.tpr',
54 input_traj_path='/path/to/myTrajectory.trr',
55 input_index_path='/path/to/myIndex.ndx',
56 output_pdb_path='/path/to/newStructure.pdb',
57 properties=prop)
59 Info:
60 * wrapped_software:
61 * name: GROMACS cluster
62 * version: >=2024.5
63 * license: LGPL 2.1
64 * ontology:
65 * name: EDAM
66 * schema: http://edamontology.org/EDAM.owl
68 """
70 def __init__(self, input_structure_path, input_traj_path, output_pdb_path,
71 input_index_path=None, output_cluster_log_path=None, output_rmsd_cluster_xpm_path=None,
72 output_rmsd_dist_xvg_path=None, properties=None, **kwargs) -> None:
73 properties = properties or {}
75 # Call parent class constructor
76 super().__init__(properties)
77 self.locals_var_dict = locals().copy()
79 # Input/Output files
80 self.io_dict = {
81 "in": {"input_structure_path": input_structure_path,
82 "input_traj_path": input_traj_path,
83 "input_index_path": input_index_path},
84 "out": {"output_pdb_path": output_pdb_path,
85 "output_cluster_log_path": output_cluster_log_path,
86 "output_rmsd_cluster_xpm_path": output_rmsd_cluster_xpm_path,
87 "output_rmsd_dist_xvg_path": output_rmsd_dist_xvg_path}
88 }
90 # Properties specific for BB
91 self.fit_selection = properties.get('fit_selection', "System")
92 self.output_selection = properties.get('output_selection', "System")
93 self.method = properties.get('method', "linkage")
94 self.dista = properties.get('dista', False)
95 self.nofit = properties.get('nofit', False)
96 self.cutoff = properties.get('cutoff', 0.1)
97 self.properties = properties
99 # Properties common in all GROMACS BB
100 self.binary_path = get_binary_path(properties, 'binary_path')
102 # Check the properties
103 self.check_init(properties)
105 def check_data_params(self, out_log, err_log):
106 """ Checks all the input/output paths and parameters """
107 self.io_dict["in"]["input_structure_path"] = check_input_path(self.io_dict["in"]["input_structure_path"], out_log, self.__class__.__name__)
108 self.io_dict["in"]["input_traj_path"] = check_traj_path(self.io_dict["in"]["input_traj_path"], out_log, self.__class__.__name__)
109 self.io_dict["in"]["input_index_path"] = check_index_path(self.io_dict["in"]["input_index_path"], out_log, self.__class__.__name__)
110 self.io_dict["out"]["output_pdb_path"] = check_out_pdb_path(self.io_dict["out"]["output_pdb_path"], out_log, self.__class__.__name__)
111 if not self.io_dict["in"]["input_index_path"]:
112 self.fit_selection = get_image_selection(self.properties, 'fit_selection', out_log, self.__class__.__name__)
113 self.output_selection = get_image_selection(self.properties, 'output_selection', out_log, self.__class__.__name__)
114 else:
115 self.fit_selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'fit_selection', out_log, self.__class__.__name__)
116 self.output_selection = get_selection_index_file(self.properties, self.io_dict["in"]["input_index_path"], 'output_selection', out_log, self.__class__.__name__)
117 self.dista = get_dista(self.properties, out_log, self.__class__.__name__)
118 self.method = get_method(self.properties, out_log, self.__class__.__name__)
119 self.cutoff = get_cutoff(self.properties, out_log, self.__class__.__name__)
121 @launchlogger
122 def launch(self) -> int:
123 """Execute the :class:`GMXCluster <gromacs.gmx_cluster.GMXCluster>` object."""
125 # check input/output paths and parameters
126 self.check_data_params(self.out_log, self.err_log)
128 # Setup Biobb
129 if self.check_restart():
130 return 0
132 # standard input
133 self.io_dict['in']['stdin_file_path'] = fu.create_stdin_file(f'{self.fit_selection} {self.output_selection}')
134 self.stage_files()
136 # Optional output files
137 dist = self.stage_io_dict['out'].get('output_rmsd_dist_xvg_path') or self.create_tmp_file('rmsd-dist.xvg')
138 rmsd = self.stage_io_dict['out'].get('output_rmsd_cluster_xpm_path') or self.create_tmp_file('rmsd-clust.xpm')
139 clust = self.stage_io_dict['out'].get('output_cluster_log_path') or self.create_tmp_file('cluster.log')
141 self.cmd = [self.binary_path, 'cluster',
142 '-g', clust,
143 '-dist', dist,
144 '-o', rmsd,
145 '-s', self.stage_io_dict["in"]["input_structure_path"],
146 '-f', self.stage_io_dict["in"]["input_traj_path"],
147 '-cl', self.stage_io_dict["out"]["output_pdb_path"],
148 '-cutoff', str(self.cutoff),
149 '-method', self.method]
151 if self.stage_io_dict["in"].get("input_index_path"):
152 self.cmd.extend(['-n', self.stage_io_dict["in"]["input_index_path"]])
154 if self.dista:
155 self.cmd.append('-dista')
157 if self.nofit:
158 self.cmd.append('-nofit')
160 # Add stdin input file
161 self.cmd.append('<')
162 self.cmd.append(self.stage_io_dict["in"]["stdin_file_path"])
164 # Run Biobb block
165 self.run_biobb()
166 # Copy files to host
167 self.copy_to_host()
168 self.tmp_files.append(self.io_dict['in'].get("stdin_file_path", ""))
169 self.remove_tmp_files()
170 self.check_arguments(output_files_created=True, raise_exception=False)
172 return self.return_code
175def gmx_cluster(input_structure_path: str,
176 input_traj_path: str,
177 output_pdb_path: str,
178 input_index_path: Optional[str] = None,
179 output_cluster_log_path: Optional[str] = None,
180 output_rmsd_cluster_xpm_path: Optional[str] = None,
181 output_rmsd_dist_xvg_path: Optional[str] = None,
182 properties: Optional[dict] = None,
183 **kwargs) -> int:
184 """Execute the :class:`GMXCluster <gromacs.gmx_cluster.GMXCluster>` class and
185 execute the :meth:`launch() <gromacs.gmx_cluster.GMXCluster.launch>` method."""
186 return GMXCluster(**dict(locals())).launch()
189gmx_cluster.__doc__ = GMXCluster.__doc__
190main = GMXCluster.get_main(gmx_cluster, "Creates cluster structures from a given GROMACS compatible trajectory.")
192if __name__ == '__main__':
193 main()